state: generation 5155 (cycle)

This commit is contained in:
2026-09-10 12:16:54 +00:00
parent 12bf25197e
commit 336957ac17
10 changed files with 1999 additions and 1975 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T12:06:09.429869+00:00",
"lastSyncTime": "2026-09-10T12:06:09.109223+00:00",
"generatedAt": "2026-09-10T12:15:14.576026+00:00",
"lastSyncTime": "2026-09-10T12:15:14.346623+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1793,29 +1793,29 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 70,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 80,
"attributableFailureCount": 71,
"decisionFailureRate": 0.8765,
"decisionSuccessRate": 0.1235,
"decisionTotal": 81,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 46,
"framework_architecture_unsupported": 47,
"memory_capacity": 1,
"model_load": 23,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 136,
"failureRate": 0.9315,
"failureCount": 137,
"failureRate": 0.932,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 10,
"successRate": 0.0685,
"successRate": 0.068,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 146,
"total": 147,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -1868,10 +1868,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 28,
"ambiguous_runtime": 29,
"参数/模板问题": 1
},
"failureCount": 29,
"failureCount": 30,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -1881,8 +1881,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 29,
"unresolvedFailureCount": 29
"total": 30,
"unresolvedFailureCount": 30
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2008,9 +2008,10 @@
"memory_capacity": 1,
"model_load": 2,
"repository_structure": 1,
"runtime_memory": 2
"runtime_memory": 2,
"参数/模板问题": 3
},
"failureCount": 59,
"failureCount": 62,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2020,8 +2021,8 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 59,
"unresolvedFailureCount": 27
"total": 62,
"unresolvedFailureCount": 30
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2292,28 +2293,28 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 123,
"decisionFailureRate": 0.7193,
"decisionSuccessRate": 0.2807,
"decisionTotal": 171,
"attributableFailureCount": 124,
"decisionFailureRate": 0.7209,
"decisionSuccessRate": 0.2791,
"decisionTotal": 172,
"failureBreakdown": {
"ambiguous_runtime": 115,
"backend_operator": 3,
"framework_architecture_unsupported": 87,
"framework_architecture_unsupported": 88,
"memory_capacity": 5,
"model_load": 25,
"tokenizer_compatibility": 3,
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 967,
"failureRate": 0.9527,
"failureCount": 968,
"failureRate": 0.9528,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 48,
"successRate": 0.0473,
"total": 1015,
"successRate": 0.0472,
"total": 1016,
"unresolvedFailureCount": 844
},
"vllm": {
@@ -2331,17 +2332,17 @@
"repository_structure": 5,
"runtime_memory": 5,
"tokenizer_compatibility": 3,
"参数/模板问题": 21
"参数/模板问题": 24
},
"failureCount": 424,
"failureRate": 0.9976,
"failureCount": 427,
"failureRate": 0.9977,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.0024,
"total": 425,
"unresolvedFailureCount": 188
"successRate": 0.0023,
"total": 428,
"unresolvedFailureCount": 191
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2408,22 +2409,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 29,
"ambiguous_runtime": 30,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 2,
"tokenizer_compatibility": 32,
"参数/模板问题": 7
},
"failureCount": 75,
"failureCount": 76,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 75,
"unresolvedFailureCount": 36
"total": 76,
"unresolvedFailureCount": 37
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 0,
@@ -2444,7 +2445,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T12:06:09.421970+00:00",
"generatedAt": "2026-09-10T12:15:14.571193+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2607,26 +2608,26 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 70,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 80,
"attributableFailureCount": 71,
"decisionFailureRate": 0.8765,
"decisionSuccessRate": 0.1235,
"decisionTotal": 81,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 46,
"framework_architecture_unsupported": 47,
"memory_capacity": 1,
"model_load": 23,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 136,
"failureRate": 0.9315,
"failureCount": 137,
"failureRate": 0.932,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 10,
"successRate": 0.0685,
"total": 146,
"successRate": 0.068,
"total": 147,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800": {
@@ -2635,20 +2636,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 60,
"ambiguous_runtime": 61,
"memory_capacity": 1,
"参数/模板问题": 1,
"验证失败": 23
},
"failureCount": 85,
"failureCount": 86,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 85,
"unresolvedFailureCount": 84
"total": 86,
"unresolvedFailureCount": 85
},
"MetaX_c-500": {
"attributableFailureCount": 42,
@@ -2687,18 +2688,18 @@
"model_load": 3,
"repository_structure": 1,
"runtime_memory": 2,
"参数/模板问题": 7,
"参数/模板问题": 10,
"验证失败": 26
},
"failureCount": 93,
"failureRate": 0.9789,
"failureCount": 96,
"failureRate": 0.9796,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0211,
"total": 95,
"unresolvedFailureCount": 60
"successRate": 0.0204,
"total": 98,
"unresolvedFailureCount": 63
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 35,
@@ -3482,9 +3483,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
"ambiguous_runtime": 6
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "starcoder2",
@@ -3496,8 +3497,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
"total": 6,
"unresolvedFailureCount": 6
},
"MetaX_c-500|vllm|text-generation|aquila3|none": {
"attributableFailureCount": 0,
@@ -4250,7 +4251,7 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 16,
"consecutiveFailures": 3,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8421,
"decisionSuccessRate": 0.1579,
@@ -4264,7 +4265,7 @@
"failureRate": 0.85,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T12:06:09.109223+00:00",
"lastTerminalAt": "2026-09-10T12:15:14.346623+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -6214,6 +6215,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 31,
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -7005,41 +7030,41 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1572,
"totalRecords": 1659,
"terminalRecords": 1577,
"totalRecords": 1664,
"totals": {
"attributableFailureCount": 412,
"decisionFailureRate": 0.8898,
"decisionSuccessRate": 0.1102,
"decisionTotal": 463,
"attributableFailureCount": 413,
"decisionFailureRate": 0.8901,
"decisionSuccessRate": 0.1099,
"decisionTotal": 464,
"failureBreakdown": {
"ambiguous_runtime": 338,
"ambiguous_runtime": 339,
"backend_operator": 35,
"framework_architecture_unsupported": 271,
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
"model_load": 47,
"platform_infrastructure": 3,
"repository_structure": 5,
"runtime_memory": 5,
"tokenizer_compatibility": 38,
"参数/模板问题": 95,
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1521,
"failureRate": 0.9676,
"failureCount": 1526,
"failureRate": 0.9677,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 51,
"successRate": 0.0324,
"total": 1572,
"unresolvedFailureCount": 1106
"successRate": 0.0323,
"total": 1577,
"unresolvedFailureCount": 1110
},
"warnings": [
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
@@ -7047,7 +7072,7 @@
"GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7068,6 +7093,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1659,
"summarizedRecords": 1664,
"version": 1
}